Kafetzis Ioannis, Sodmann Philipp, Herghelegiu Bianca-Elena, Brand Markus, Zoller Wolfram G, Seyfried Florian, Fuchs Karl-Hermann, Meining Alexander, Hann Alexander
Interventional and Experimental Endoscopy (InExEn), Department of Internal Medicine 2, University Hospital Würzburg, Würzburg, Germany.
Department of Internal Medicine and Gastroenterology, Katharinenhospital, Stuttgart, Germany.
United European Gastroenterol J. 2025 Mar;13(2):240-246. doi: 10.1002/ueg2.12721. Epub 2024 Dec 12.
Assessment of the gastroesophageal junction (GEJ) is an integral part of gastroscopy; however, the absence of standardized reporting hinders consistency of examination documentation. The Hill classification offers a standardized approach for evaluating the GEJ. This study aims to compare the accuracy of an artificial intelligence (AI) system with that of physicians in classifying the GEJ according to Hill in a prospective, blinded, superiority trial.
Consecutive patients scheduled for gastroscopy with an intact GEJ were recruited during clinical routine from October 2023 to December 2023. Nine physicians (six experienced, three inexperienced) assessed the Hill grade, and the AI system operated in the background in real-time. The gold standard was determined by a majority vote of independent assessments by three expert endoscopists who did not participate in the study. The primary outcome was accuracy. Secondary outcomes were per-Hill grade analysis and result comparison for experienced and inexperienced endoscopists separately.
In 131 analysed examinations the AI's accuracy of 84.7% (95% CI: 78.6-90.8) was significantly higher than 62.5% (95% CI: 54.2-71) of physicians (p < 0.01). The AI outperformed physicians in all but one cases in the per-Hill-class analysis. AI was significantly more accurate than inexperienced physicians (85% vs. 56%, p < 0.01) and in trend better than experienced physicians (84% vs. 69.6%, p = 0.07).
AI was significantly more accurate than examiners in assessing the Hill classification. This superior model performance can prove beneficial for endoscopists, especially those with limited experience.
ClinicalTrials.gov identifier: NCT06040723.
胃食管交界部（GEJ）的评估是胃镜检查的一个重要组成部分；然而，缺乏标准化报告阻碍了检查记录的一致性。希尔分类法为评估GEJ提供了一种标准化方法。本研究旨在通过一项前瞻性、双盲、优效性试验，比较人工智能（AI）系统与医生根据希尔分类法对GEJ进行分类的准确性。
在2023年10月至2023年12月的临床常规工作中，连续招募计划进行胃镜检查且GEJ完整的患者。九名医生（六名经验丰富，三名经验不足）评估希尔分级，AI系统在后台实时运行。金标准由三名未参与研究的专家内镜医师独立评估的多数投票确定。主要结局是准确性。次要结局是按希尔分级分析以及分别对经验丰富和经验不足的内镜医师的结果进行比较。
在131例分析的检查中，AI的准确性为84.7%（95%CI：78.6 - 90.8），显著高于医生的62.5%（95%CI：54.2 - 71）（p < 0.01）。在按希尔分级的分析中，除一例病例外，AI在所有病例中均优于医生。AI比经验不足的医生显著更准确（85%对56%，p < 0.01），且在趋势上比经验丰富的医生更好（84%对69.6%，p = 0.07）。
在评估希尔分类法时，AI比检查者显著更准确。这种优越的模型性能可能对内镜医师有益，尤其是那些经验有限的医师。
ClinicalTrials.gov标识符：NCT06040723。
